<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="auersperger-pecina-2021-solving">
    <titleInfo>
        <title>Solving SCAN Tasks with Data Augmentation and Input Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Michal</namePart>
        <namePart type="family">Auersperger</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pavel</namePart>
        <namePart type="family">Pecina</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd.</publisher>
            <place>
                <placeTerm type="text">Held Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We address the compositionality challenge presented by the SCAN benchmark. Using data augmentation and a modification of the standard seq2seq architecture with attention, we achieve SOTA results on all the relevant tasks from the benchmark, showing the models can generalize to words used in unseen contexts. We propose an extension of the benchmark by a harder task, which cannot be solved by the proposed method.</abstract>
    <identifier type="citekey">auersperger-pecina-2021-solving</identifier>
    <location>
        <url>https://aclanthology.org/2021.ranlp-1.11</url>
    </location>
    <part>
        <date>2021-09</date>
        <extent unit="page">
            <start>86</start>
            <end>91</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Solving SCAN Tasks with Data Augmentation and Input Embeddings
%A Auersperger, Michal
%A Pecina, Pavel
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F auersperger-pecina-2021-solving
%X We address the compositionality challenge presented by the SCAN benchmark. Using data augmentation and a modification of the standard seq2seq architecture with attention, we achieve SOTA results on all the relevant tasks from the benchmark, showing the models can generalize to words used in unseen contexts. We propose an extension of the benchmark by a harder task, which cannot be solved by the proposed method.
%U https://aclanthology.org/2021.ranlp-1.11
%P 86-91

Markdown (Informal)

[Solving SCAN Tasks with Data Augmentation and Input Embeddings](https://aclanthology.org/2021.ranlp-1.11) (Auersperger & Pecina, RANLP 2021)

• Solving SCAN Tasks with Data Augmentation and Input Embeddings (Auersperger & Pecina, RANLP 2021)

ACL

• Michal Auersperger and Pavel Pecina. 2021. Solving SCAN Tasks with Data Augmentation and Input Embeddings. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 86–91, Held Online. INCOMA Ltd..